Blake Richards

ali.sahebpasand@mila.quebec

Ali Saheb Pasand

Doctorat - McGill University

Superviseur⋅e principal⋅e :

Pouya Bashivan

Alissia Di Maria

Stagiaire de recherche - McGill University

alissia.dimaria@mila.quebec

Ann Huang

Collaborateur·rice alumni

zixiang.huang@mila.quebec

Arna Ghosh

Doctorat - McGill University

Chen Chen

Postdoctorat - Université de Montréal

Superviseur⋅e principal⋅e :

Yoshua Bengio

chen.sun@mila.quebec

Colin Bredenberg

Postdoctorat - Université de Montréal

Superviseur⋅e principal⋅e :

colin.bredenberg@mila.quebec

Dane Malenfant

Maîtrise recherche - McGill University

dane.malenfant@mila.quebec

daniel.levenstein@mila.quebec

Daniel Levenstein

Postdoctorat - McGill University

divyansha.lachi@mila.quebec

Divyansha Lachi

Collaborateur·rice de recherche - Georgia Tech

erica.cianfarano@mila.quebec

Dongyan Lin

Doctorat - McGill University

lindongy@mila.quebec

Erica Cianfarano

Doctorat - McGill University

Ethan Caballero

Doctorat - McGill University

Co-superviseur⋅e :

Irina Rish

ethan.caballero@mila.quebec

etienne.barou-laforie@mila.quebec

Etienne Barou-Laforie

Stagiaire de recherche - McGill University

Jonathan Cornford

Postdoctorat - McGill University

cornforj@mila.quebec

Josh Tindall

Maîtrise recherche - McGill University

joshua.tindall@mila.quebec

Mandana Samiei

Doctorat - McGill University

Superviseur⋅e principal⋅e :

Doctorat - McGill University

Mohammad Yaghoubi

Doctorat - McGill University

yaghoubm@mila.quebec

Quinn Lee

Postdoctorat - McGill University

j.quinn.lee@mila.quebec

Ray Chua

Doctorat - McGill University

Superviseur⋅e principal⋅e :

Doina Precup

chuaraym@mila.quebec

Roman Pogodin

Postdoctorat - McGill University

Co-superviseur⋅e :

Roman.Pogodin@mila.Quebec

Doctorat - McGill University

roy.eyono@mila.quebec

santiago.jaramillo@mila.quebec

Santiago Jaramillo

Visiteur de recherche indépendant - University of Oregon

Sonia Joseph

Doctorat - McGill University

sonia.joseph@mila.quebec

vemund.schoyen@mila.quebec

Surya Penmetsa

Collaborateur·rice alumni

penmetss@mila.quebec

Vemund Schoyen

Stagiaire de recherche - University of Oslo

Krystal Pan

Maîtrise recherche - McGill University

xuejing.pan@mila.quebec

Billets de blogue

13 juin 2024

Que nous apprennent les distributions des coefficients synaptiques au sujet de l’apprentissage dans le cerveau ?

par

Roman Pogodin

Jonathan Cornford

Arna Ghosh

Gauthier Gidel

Guillaume Lajoie

Blake Richards

Lire l'article

α-ReQ: Assessing Representation Quality in SSL

29 août 2023

α-ReQ : Évaluation de la qualité des représentations en apprentissage auto-supervisé

par

KK Agrawal

Arnab Kumar-Mondal

Arna Ghosh

Blake A. Richards

Lire l'article

Publications

Stimulus information guides the emergence of behavior-related signals in primary somatosensory cortex during learning.

Mariangela Panniello

Colleen J Gillon

Roberto Maffulli

Marco Celotto

Stefano Panzeri

Michael M Kohl

2024-05-25

Cell Reports (publié)

Sequential predictive learning is a unifying theory for hippocampal representation and replay

Daniel Levenstein

Aleksei Efremov

Roy Henha Eyono

Adrien Peyrache

The mammalian hippocampus contains a cognitive map that represents an animal’s position in the environment 1 and generates offline “repl… (voir plus)ay” 2,3 for the purposes of recall 4, planning 5,6, and forming long term memories 7. Recently, it’s been found that artificial neural networks trained to predict sensory inputs develop spatially tuned cells 8, aligning with predictive theories of hippocampal function 9–11. However, whether predictive learning can also account for the ability to produce offline replay is unknown. Here, we find that spatially tuned cells, which robustly emerge from all forms of predictive learning, do not guarantee the presence of a cognitive map with the ability to generate replay. Offline simulations only emerged in networks that used recurrent connections and head-direction information to predict multi-step observation sequences, which promoted the formation of a continuous attractor reflecting the geometry of the environment. These offline trajectories were able to show wake-like statistics, autonomously replay recently experienced locations, and could be directed by a virtual head direction signal. Further, we found that networks trained to make cyclical predictions of future observation sequences were able to rapidly learn a cognitive map and produced sweeping representations of future positions reminiscent of hippocampal theta sweeps 12. These results demonstrate how hippocampal-like representation and replay can emerge in neural networks engaged in predictive learning, and suggest that hippocampal theta sequences reflect a circuit that implements a data-efficient algorithm for sequential predictive learning. Together, this framework provides a unifying theory for hippocampal functions and hippocampal-inspired approaches to artificial intelligence.

2024-04-29

bioRxiv (prépublication)

Fast burst fraction transients convey information independent of the firing rate

Richard Naud

Xingyun Wang

Zachary Friedenberger

Alexandre Payeur

Jiyun N. Shin

Jean-Claude Béïque

Moritz Drüke

Matthew E. Larkum

Guy Doron

Theories of attention and learning have hypothesized a central role for high-frequency bursting in cognitive functions, but experimental rep… (voir plus)orts of burst-mediated representations in vivo have been limited. Here we used a novel demultiplexing approach by considering a conjunctive burst code. We studied this code in vivo while animals learned to report direct electrical stimulation of the somatosensory cortex and found two acquired yet independent representations. One code, the event rate, showed a sparse and succint stiumulus representation and a small modulation upon detection errors. The other code, the burst fraction, correlated more globally with stimulation and more promptly responded to detection errors. Bursting modulation was potent and its time course evolved, even in cells that were considered unresponsive based on the firing rate. During the later stages of training, this modulation in bursting happened earlier, gradually aligning temporally with the representation in event rate. The alignment of bursting and event rate modulation sharpened the firing rate response, and was strongly associated behavioral accuracy. Thus a fine-grained separation of spike timing patterns reveals two signals that accompany stimulus representations: an error signal that can be essential to guide learning and a sharpening signal that could implement attention mechanisms.

2024-03-27

bioRxiv (prépublication)

Sufficient conditions for offline reactivation in recurrent neural networks

Nanda H Krishna

Colin Bredenberg

Daniel Levenstein

During periods of quiescence, such as sleep, neural activity in many brain circuits resembles that observed during periods of task engagemen… (voir plus)t. However, the precise conditions under which task-optimized networks can autonomously reactivate the same network states responsible for online behavior is poorly understood. In this study, we develop a mathematical framework that outlines sufficient conditions for the emergence of neural reactivation in circuits that encode features of smoothly varying stimuli. We demonstrate mathematically that noisy recurrent networks optimized to track environmental state variables using change-based sensory information naturally develop denoising dynamics, which, in the absence of input, cause the network to revisit state configurations observed during periods of online activity. We validate our findings using numerical experiments on two canonical neuroscience tasks: spatial position estimation based on self-motion cues, and head direction estimation based on angular velocity cues. Overall, our work provides theoretical support for modeling offline reactivation as an emergent consequence of task optimization in noisy neural circuits.

2024-01-16

ICLR.cc/2024/Conference (poster)

Synaptic Weight Distributions Depend on the Geometry of Plasticity

Roman Pogodin

Jonathan Cornford

Arna Ghosh

Gauthier Gidel

A growing literature in computational neuroscience leverages gradient descent and learning algorithms that approximate it to study synaptic … (voir plus)plasticity in the brain. However, the vast majority of this work ignores a critical underlying assumption: the choice of distance for synaptic changes - i.e. the geometry of synaptic plasticity. Gradient descent assumes that the distance is Euclidean, but many other distances are possible, and there is no reason that biology necessarily uses Euclidean geometry. Here, using the theoretical tools provided by mirror descent, we show that the distribution of synaptic weights will depend on the geometry of synaptic plasticity. We use these results to show that experimentally-observed log-normal weight distributions found in several brain areas are not consistent with standard gradient descent (i.e. a Euclidean geometry), but rather with non-Euclidean distances. Finally, we show that it should be possible to experimentally test for different synaptic geometries by comparing synaptic weight distributions before and after learning. Overall, our work shows that the current paradigm in theoretical work on synaptic plasticity that assumes Euclidean synaptic geometry may be misguided and that it should be possible to experimentally determine the true geometry of synaptic plasticity in the brain.

2024-01-16

ICLR.cc/2024/Conference (spotlight)

Addressing Sample Inefficiency in Multi-View Representation Learning

Kumar Krishna Agrawal

Arna Ghosh

Adam M. Oberman

2023-12-17

ArXiv (prépublication)

Temporal encoding in deep reinforcement learning agents

Dongyan Lin

Ann Zixiang Huang

2023-12-15

Scientific Reports (publié)

On the Information Geometry of Vision Transformers

Sonia Joseph

Kumar Krishna Agrawal

Arna Ghosh

2023-11-28

NeurIPS.cc/2023/Workshop/NeurReps (poster)

On the Varied Faces of Overparameterization in Supervised and Self-Supervised Learning

Matteo Gamba

Arna Ghosh

Kumar Krishna Agrawal

Agrawal

Hossein Azizpour

Mårten Björkman

The quality of the representations learned by neural networks depends on several factors, including the loss function, learning algorithm, a… (voir plus)nd model architecture. In this work, we use information geometric measures to assess the representation quality in a principled manner. We demonstrate that the sensitivity of learned representations to input perturbations, measured by the spectral norm of the feature Jacobian, provides valuable information about downstream generalization. On the other hand, measuring the coefficient of spectral decay observed in the eigenspectrum of feature covariance provides insights into the global representation geometry. First, we empirically establish an equivalence between these notions of representation quality and show that they are inversely correlated. Second, our analysis reveals the varying roles that overparameterization plays in improving generalization. Unlike supervised learning, we observe that increasing model width leads to higher discriminability and less smoothness in the self-supervised regime. Furthermore, we report that there is no observable double descent phenomenon in SSL with non-contrastive objectives for commonly used parameterization regimes, which opens up new opportunities for tight asymptotic analysis. Taken together, our results provide a loss-aware characterization of the different role of overparameterization in supervised and self-supervised learning.

2023-11-28

NeurIPS.cc/2023/Workshop/NeurReps (poster)

Learning from unexpected events in the neocortical microcircuit

Colleen J Gillon

Jason E. Pina

Jérôme A. Lecoq

Ruweida Ahmed

Yazan N. Billeh

Shiella Caldejon

Peter Groblewski

Timothy M. Henley

India Kato

Eric Lee

Jennifer Luviano

Kyla Mace

Chelsea Nayan

Thuyanh V. Nguyen

Kat North

Jed Perkins

Sam Seid

Matthew T. Valley

Ali Williford

Yoshua Bengio … (voir 3 de plus)

Timothy P. Lillicrap

Joel Zylberberg

2023-11-21

Journal of Neuroscience (publié)

Responses to Pattern-Violating Visual Stimuli Evolve Differently Over Days in Somata and Distal Apical Dendrites

Colleen J Gillon

Jason E. Pina

Jérôme A. Lecoq

Ruweida Ahmed

Yazan N. Billeh

Shiella Caldejon

Peter Groblewski

Timothy M. Henley

India Kato

Eric Lee

Jennifer Luviano

Kyla Mace

Chelsea Nayan

Thuyanh V. Nguyen

Kat North

Jed Perkins

Sam Seid

Matthew T. Valley

Ali Williford

Yoshua Bengio … (voir 3 de plus)

Timothy P. Lillicrap

Joel Zylberberg

Scientists have long conjectured that the neocortex learns patterns in sensory data to generate top-down predictions of upcoming stimuli. In… (voir plus) line with this conjecture, different responses to pattern-matching vs pattern-violating visual stimuli have been observed in both spiking and somatic calcium imaging data. However, it remains unknown whether these pattern-violation signals are different between the distal apical dendrites, which are heavily targeted by top-down signals, and the somata, where bottom-up information is primarily integrated. Furthermore, it is unknown how responses to pattern-violating stimuli evolve over time as an animal gains more experience with them. Here, we address these unanswered questions by analyzing responses of individual somata and dendritic branches of layer 2/3 and layer 5 pyramidal neurons tracked over multiple days in primary visual cortex of awake, behaving female and male mice. We use sequences of Gabor patches with patterns in their orientations to create pattern-matching and pattern-violating stimuli, and two-photon calcium imaging to record neuronal responses. Many neurons in both layers show large differences between their responses to pattern-matching and pattern-violating stimuli. Interestingly, these responses evolve in opposite directions in the somata and distal apical dendrites, with somata becoming less sensitive to pattern-violating stimuli and distal apical dendrites more sensitive. These differences between the somata and distal apical dendrites may be important for hierarchical computation of sensory predictions and learning, since these two compartments tend to receive bottom-up and top-down information, respectively.

2023-11-21

Journal of Neuroscience (publié)

The feature landscape of visual cortex

Rudi Tong

Ronan da Silva

Dongyan Lin

Arna Ghosh

James Wilsenach

Erica Cianfarano

Pouya Bashivan

Stuart Trenholm

Understanding computations in the visual system requires a characterization of the distinct feature preferences of neurons in different visu… (voir plus)al cortical areas. However, we know little about how feature preferences of neurons within a given area relate to that area’s role within the global organization of visual cortex. To address this, we recorded from thousands of neurons across six visual cortical areas in mouse and leveraged generative AI methods combined with closed-loop neuronal recordings to identify each neuron’s visual feature preference. First, we discovered that the mouse’s visual system is globally organized to encode features in a manner invariant to the types of image transformations induced by self-motion. Second, we found differences in the visual feature preferences of each area and that these differences generalized across animals. Finally, we observed that a given area’s collection of preferred stimuli (‘own-stimuli’) drive neurons from the same area more effectively through their dynamic range compared to preferred stimuli from other areas (‘other-stimuli’). As a result, feature preferences of neurons within an area are organized to maximally encode differences among own-stimuli while remaining insensitive to differences among other-stimuli. These results reveal how visual areas work together to efficiently encode information about the external world.

2023-11-05

bioRxiv (prépublication)